Add /tldr: a private overview of what you missed in a channel

/tldr [since] summarizes the messages in the channel it is run in that the
caller has not been summarized yet, using a small local model on Ollama, and
replies ephemerally. The answer streams into the reply as it is written.

- Per-user, per-channel cursor (tldr_cursors) so each run picks up where the
  last left off; `since:` (e.g. 6h, 2d, max 7d) peeks without moving it.
  First use covers the last 24h, and a stale cursor never reaches back more
  than 7 days.
- Only summarizes channels both the caller and the bot can read.
- The transcript drops bots, system messages, reactions and filler, turns
  links, GIFs, images and files into short tags ([link: site], [image],
  [file: name], preview titles), marks replies, and writes a date marker
  where the chat paused for 3h or more so the model can keep topics apart.
- The prompt asks for one bullet per conversation, oldest first, with a
  worked example; it was tuned against a synthetic chat and a real export
  with qwen3:4b-instruct-2507 (the default model).
- One model call at a time across the bot, one /tldr per user.
- docker-compose: Ollama service (CPU only, 8g memory cap: 6g killed the
  runner mid-request), model pull on startup.

Needs the tldr_cursors migration (velox-dashboard-api 000016).

Co-Authored-By: Claude Opus 5.5 <[email protected]>

README.md

@@ -44,6 +44,12 @@ Optional (Twitch live notifications):
 
 - `TWITCH_CLIENT_ID`: Twitch Client ID used to query live status
 
+Optional (`/tldr` summaries, needs an [Ollama](https://ollama.com) server; the compose file includes one):
+
+- `OLLAMA_HOST`: Ollama base URL (default `http://ollama:11434`)
+- `TLDR_MODEL`: Ollama model tag (default `qwen3:4b-instruct-2507-q4_K_M`)
+- `TLDR_THREADS`: CPU threads the model may use (default `6`; keep it well below your core count)
+
 ## Database setup
 
 If you use the compose file: